Search Results for author: Seba Susan

Found 15 papers, 6 papers with code

Epidemic Modeling using Hybrid of Time-varying SIRD, Particle Swarm Optimization, and Deep Learning

no code implementations31 Jan 2024 Naresh Kumar, Seba Susan

In our model, we use a system of ordinary differential equations (ODEs) for Susceptible-Infected-Recovered-Dead (SIRD) epidemic modeling, Particle Swarm Optimization (PSO) for model parameter optimization, and stacked-LSTM for forecasting the model parameters.

CovSumm: an unsupervised transformer-cum-graph-based hybrid document summarization model for CORD-19

no code implementations The Journal of Supercomputing 2023 Akanksha Karotia, Seba Susan

To address information overload in COVID-19 scientific literature, the study presents a novel hybrid model named CovSumm, an unsupervised graph-based hybrid approach for single-document summarization, that is evaluated on the CORD-19 dataset.

Document Summarization Extractive Text Summarization +1

v-TCM: Vertical-aware Transformer Click Model for Web Search

no code implementations 37th ACM/SIGAPP Symposium on Applied Computing 2022 Kritarth Bisht, Seba Susan

A novel transformer model is proposed in this paper for click prediction and relevance estimation that learns additionally from the vertical information, apart from the query and search engine results that are the inputs for the traditional click models.

Click-Through Rate Prediction

Emotion-Aware Transformer Encoder for Empathetic Dialogue Generation

1 code implementation 2021 9th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) 2021 Raman Goel, Seba Susan, Sachin Vashisht, Armaan Dhanda

The contributions of our paper are as follows: 1) An emotion detector module trained on the input utterances determines the affective state of the user in the initial phase 2) A novel transformer encoder is proposed that adds and normalizes the word embedding with emotion embedding thereby integrating the semantic and affective aspects of the input utterance 3) The encoder and decoder stacks belong to the Transformer-XL architecture which is the recent state of the art in language modeling.

Dialogue Generation Language Modelling +1

VGGIN-Net: Deep Transfer Network for Imbalanced Breast Cancer Dataset


In this paper, we have presented a novel deep neural network architecture involving transfer learning approach, formed by freezing and concatenating all the layers till block4 pool layer of VGG16 pre-trained model (at the lower level) with the layers of a randomly initialized naïve Inception block module (at the higher level).

Breast Cancer Detection Data Augmentation +2

Improving Word Recognition in Speech Transcriptions by Decision-level Fusion of Stemming and Two-way Phoneme Pruning

no code implementations26 Jul 2021 Sunakshi Mehra, Seba Susan

In our approach we tried to improve the baseline accuracy from 9. 34% by using stemming, phoneme extraction, filtering and pruning.

A Hybrid Model for Combining Neural Image Caption and k-Nearest Neighbor Approach for Image Captioning

1 code implementation9 May 2021 Kartik Arora, Ajul Raj, Arun Goel, Seba Susan

The BLEU-4 scores of the two models are compared for generating the binary-value ground truth for the logistic regression classifier.

Image Captioning regression

Evaluating Deep Neural Network Ensembles by Majority Voting cum Meta-Learning scheme

no code implementations9 May 2021 Anmol Jain, Aishwary Kumar, Seba Susan

So instead of using a single DNN as classifier we propose an ensemble of seven independent DNN learners by varying only the input to these DNNs keeping their architecture and intrinsic properties same.

Human Activity Recognition Meta-Learning

A Novel Framework for Neural Architecture Search in the Hill Climbing Domain

no code implementations22 Feb 2021 Mudit Verma, Pradyumna Sinha, Karan Goyal, Apoorva Verma, Seba Susan

Neural networks have now long been used for solving complex problems of image domain, yet designing the same needs manual expertise.

Neural Architecture Search Reinforcement Learning (RL)

Context- and Sequence-Aware Convolutional Recurrent Encoder for Neural Machine Translation

no code implementations11 Jan 2021 Ritam Mallick, Seba Susan, Vaibhaw Agrawal, Rizul Garg, Prateek Rawal

We incorporate the goodness of both approaches by proposing a convolutional-recurrent encoder for capturing the context information as well as the sequential information from the source sentence.

Machine Translation Sentence +1

Speaker Recognition using SincNet and X-Vector Fusion

no code implementations5 Apr 2020 Mayank Tripathi, Divyanshu Singh, Seba Susan

The idea behind using SincNet filters on the raw speech waveform is to extract more distinguishing frequency-related features in the initial convolution layers of the CNN architecture.

Speaker Recognition

A non-extensive entropy feature and its application to texture classification

no code implementations8 Mar 2016 Seba Susan, Madasu Hanmandlu

This paper proposes a new probabilistic non-extensive entropy feature for texture characterization, based on a Gaussian information measure.

General Classification Texture Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.